Claire E. Imrie

River flow prediction using artificial neural networks: generalisation beyond the calibration range

Abstract Artificial neural networks (ANNs) provide a quick and flexible means of creating models for river flow prediction, and have been shown to perform well in comparison with conventional methods. However, if the models are trained using a dataset that contains a limited range of values, they may perform poorly when encountering events containing previously unobserved values. This failure to generalise limits their use as a tool in applications where the data available for calibration is unlikely to cover all possible scenarios. This paper presents a method for improved generalisation during training by adding a guidance system to the cascade-correlation learning architecture. Two case studies from catchments in the UK are prepared so that the validation data contains values that are greater or less than any included in the calibration data. The ability of the developed algorithm to generalise on new data is compared with that of the standard error backpropagation algorithm. The ability of ANNs trained with different output activation functions to extrapolate beyond the calibration data is assessed.

Spatial correlation between the prevalence of transmissible spongiform diseases and British soil geochemistry.

Transmissible spongiform encephalopathies (TSEs) are a group of fatal neurological conditions affecting a number of mammals, including sheep and goats (scrapie), cows (BSE), and humans (Creutzfeldt-Jakob disease). The diseases are widely believed to be caused by the misfolding of the normal prion protein to a pathological isoform, which is thought to act as an infectious agent. Outbreaks of the disease are commonly attributed to contaminated feed and genetic susceptibility. However, the implication of copper and manganese in the pathology of the disease, and its apparent geographical clustering, have prompted suggestions of a link with trace elements in the environment. Nevertheless, studies of soils at regional scales have failed to provide evidence of an environmental risk factor. This study uses geostatistical techniques to investigate the correlations between the distribution of TSE prevalence and soil geochemical variables across the UK according to different spatial scales. A similar spatial pattern in scrapie and BSE occurrence is identified, which may be linked with increasing pH and total organic carbon, and decreasing iodine concentration. However, the pattern also resembles that of the density of dairy farming. Nevertheless, despite the low spatial resolution of the TSE data available for this study, the fact that significant correlations are detected indicates there is a possibility of a link between soil geochemistry, scrapie, and BSE. It is suggested that further investigations of the prevalence of TSE and environmental exposure to trace metals should take into account the factors affecting their bioavailability.

Coalbed methane reservoir data and simulator parameter uncertainty modelling for CO2 storage performance assessment

Abstract Laboratory studies and a number of field pilots have demonstrated that CO 2 injection into coal seams has the potential to enhance coalbed methane (CBM) recovery with the added advantage that most of the injected CO 2 can be stored permanently in coal. The concept of storing CO 2 in geologic formations as a safe and effective greenhouse gas mitigation option requires public and regulatory acceptance. In this context it is important to develop a good understanding of the reservoir performance, uncertainties and the risks that are associated with geological storage. The paper presented refers to the sources of uncertainty involved in CO 2 storage performance assessment in coalbed methane reservoirs and demonstrates their significance using extensive digital well log data representing the Manville coals in Alberta, Canada. The spatial variability of the reservoir properties was captured through geostatistical analysis, and sequential Gaussian simulations of these provided multiple realisations for the reservoir simulator inputs. A number of CO 2 injection scenarios with variable matrix swelling coefficients were evaluated using a 2D reservoir model and spatially distributed realisations of total net thickness and permeability.